CivArchive
    In Memory of Leonardo - Codex X MOSS
    NSFW
    Preview 146451222
    Preview 146451217
    Preview 146451223
    Preview 146451208
    Preview 146451210
    Preview 146451207
    Preview 146451224
    Preview 146451213
    Preview 146451211
    Preview 146451226
    Preview 146451212
    Preview 146451216
    Preview 146451221

    In Memory of Leonardo

    A style LoRA built entirely from my own urban exploration photography, years of abandoned villas, chapels, workshops and forgotten rooms, condensed into one look.

    The name is a quiet tribute. Sfumato, the soft transition from light into shadow, is what defines these places for me: a single beam through a broken window, dust in the air, and everything else slowly dissolving into darkness.

    Trigger word

    X4LSFUMATO


    Style prefixes (from the three training sets)

    X4LSFUMATO, dark cinematic color grading, deep shadows, heavy vignette
    X4LSFUMATO, warm muted film tones, soft faded colors
    X4LSFUMATO, natural warm light, documentary photo

    - Base model: Krea 2 Turbo (trained on Krea 2 Raw)

    - Strength: 1.0 – 1.4, up to 2.5 for an extreme painterly look

    Tips

    - Keep prompts short and factual: the place, the objects, where the light comes from, the camera angle. Long style or lighting descriptions override the LoRA.

    - One light source works best. A single beam onto the main subject with the rest of the room falling into shadow is exactly what it was trained on.

    - For the punchy dark look, add: teal blue shadows and warm orange highlights, high local contrast

    - It also adds decay to scenes that are not abandoned at all, but stays subtle when the prompt clearly describes an active place.

    Known limitations

    - Torn fabric (curtains, tarps) sometimes gets unnaturally round holes.

    - On surfaces like signs or license plates the trigger word can show up as text. Avoid those in the prompt or retry with another seed.

    Dataset: 72 of my own photographs, captioned by hand and with a local vision model, rank 32.

    A MOSS version is planned.

    Description

    Codex X – MOSS version.

    Trained with AI Toolkit on the same 72 urbex photographs as the Krea 2 version, 800 steps. Recommended with the MOSS-Image SFT 8-step DMD LoRA, strength 0.8 – 1.2. Adds decay, grit and the teal-orange contrast of the original photos to MOSS's clean look.

    FAQ

    LORA
    MOSS Image

    Details

    Downloads
    72
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/22/2026
    Updated
    10/25/2026
    Deleted
    -
    Trigger Words:
    X4LSFUMATO
    dark cinematic color grading
    deep shadows
    heavy vignette
    soft faded colors
    natural warm light
    documentary photo

    Files

    X4LSFUMATO_moss_CodexX.safetensors

    Mirrors